R-CONV++: uncovering privacy vulnerabilities through analytical gradient inversion attacks
<p dir="ltr">Federated learning has emerged as a prominent privacy-preserving technique for leveraging large-scale distributed datasets by sharing gradients instead of raw data. However, recent studies indicate that private training data can still be exposed through gradient inversio...
محفوظ في:
| المؤلف الرئيسي: | Tamer Ahmed Eltaras (22565414) (author) |
|---|---|
| مؤلفون آخرون: | Qutaibah Malluhi (3158757) (author), Alessandro Savino (679568) (author), Stefano Di Carlo (679569) (author), Adnan Qayyum (16875936) (author) |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
مواد مشابهة
-
Efficient Verifiable Protocol for Privacy-Preserving Aggregation in Federated Learning
حسب: Tamer Eltaras (17987005)
منشور في: (2023) -
Deep Neural Networks for Electromagnetic Inverse Scattering Problems in Microwave Imaging
حسب: Maricar, Mohammed Farook
منشور في: (2023) -
Novel Evasion Attacks Against Adversarial Training Defense for Smart Grid Federated Learning
حسب: Atef H. Bondok (19482352)
منشور في: (2023) -
Untrained Neural Network Priors for Inverse Imaging Problems: A Survey
حسب: Adnan Qayyum (16875936)
منشور في: (2022) -
Malware detection for mobile computing using secure and privacy-preserving machine learning approaches: A comprehensive survey
حسب: Faria Nawshin (21841598)
منشور في: (2024)